svn commit: r959275 - in /tika/trunk/tika-parsers/src: main/java/org/apache/tika/parser/pdf/PDFParser.java test/java/org/apache/tika/parser/pdf/ test/java/org/apache/tika/parser/pdf/PDFParserTest.java

[ni...@apache.org]

Author: nick
Date: Wed Jun 30 11:52:12 2010
New Revision: 959275

URL: http://svn.apache.org/viewvc?rev=959275&view=rev
Log:
TIKA-452 - Extract custom pdf metadata

Updates the PDF Parser to extract custom metadata. Also includes a PDFParser unit test (previously missing)

Added:
    tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/pdf/
    tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java
Modified:
    tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParser.java

Modified: tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParser.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParser.java?rev=959275&r1=959274&r2=959275&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParser.java (original)
+++ tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParser.java Wed Jun 30 11:52:12 2010
@@ -18,10 +18,16 @@ package org.apache.tika.parser.pdf;
 
 import java.io.IOException;
 import java.io.InputStream;
+import java.util.Arrays;
 import java.util.Calendar;
 import java.util.Collections;
+import java.util.List;
 import java.util.Set;
 
+import org.apache.pdfbox.cos.COSArray;
+import org.apache.pdfbox.cos.COSBase;
+import org.apache.pdfbox.cos.COSName;
+import org.apache.pdfbox.cos.COSString;
 import org.apache.pdfbox.pdmodel.PDDocument;
 import org.apache.pdfbox.pdmodel.PDDocumentInformation;
 import org.apache.tika.exception.TikaException;
@@ -103,6 +109,7 @@ public class PDFParser implements Parser
         addMetadata(metadata, "trapped", info.getTrapped());
         try {
             addMetadata(metadata, "created", info.getCreationDate());
+            addMetadata(metadata, Metadata.CREATION_DATE, info.getCreationDate());
         } catch (IOException e) {
             // Invalid date format, just ignore
         }
@@ -112,6 +119,19 @@ public class PDFParser implements Parser
         } catch (IOException e) {
             // Invalid date format, just ignore
         }
+        
+        // All remaining metadata is custom
+        // Copy this over as-is
+        List<String> handledMetadata = Arrays.asList(new String[] {
+             "Author", "Creator", "CreationData", "ModDate",
+             "Keywords", "Producer", "Subject", "Title", "Trapped"
+        });
+        for(COSName key : info.getDictionary().keySet()) {
+            String name = key.getName();
+            if(! handledMetadata.contains(name)) {
+        	addMetadata(metadata, name, info.getDictionary().getDictionaryObject(key));
+            }
+        }
     }
 
     private void addMetadata(Metadata metadata, String name, String value) {
@@ -126,4 +146,19 @@ public class PDFParser implements Parser
         }
     }
 
+    /**
+     * Used when processing custom metadata entries, as PDFBox won't do
+     *  the conversion for us in the way it does for the standard ones
+     */
+    private void addMetadata(Metadata metadata, String name, COSBase value) {
+        if(value instanceof COSArray) {
+            for(COSBase v : ((COSArray)value).toList()) {
+                addMetadata(metadata, name, v);
+            }
+        } else if(value instanceof COSString) {
+            addMetadata(metadata, name, ((COSString)value).getString());
+        } else {
+            addMetadata(metadata, name, value.toString());
+        }
+    }
 }

Added: tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java?rev=959275&view=auto
==============================================================================
--- tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java (added)
+++ tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java Wed Jun 30 11:52:12 2010
@@ -0,0 +1,63 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements.  See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License.  You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.tika.parser.pdf;
+
+import java.io.InputStream;
+
+import junit.framework.TestCase;
+
+import org.apache.tika.metadata.Metadata;
+import org.apache.tika.parser.AutoDetectParser;
+import org.apache.tika.parser.ParseContext;
+import org.apache.tika.parser.Parser;
+import org.apache.tika.sax.BodyContentHandler;
+import org.xml.sax.ContentHandler;
+
+/**
+ * Test case for parsing pdf files.
+ */
+public class PDFParserTest extends TestCase {
+
+    public void testPdfParsing() throws Exception {
+        Parser parser = new AutoDetectParser(); // Should auto-detect!
+        ContentHandler handler = new BodyContentHandler();
+        Metadata metadata = new Metadata();
+        ParseContext context = new ParseContext();
+
+        InputStream stream = PDFParserTest.class.getResourceAsStream(
+                "/test-documents/testPDF.pdf");
+        try {
+            parser.parse(stream, handler, metadata, context);
+        } finally {
+            stream.close();
+        }
+
+        assertEquals("application/pdf", metadata.get(Metadata.CONTENT_TYPE));
+        assertEquals("Bertrand Delacrétaz", metadata.get(Metadata.AUTHOR));
+        assertEquals("Apache Tika - Apache Tika", metadata.get(Metadata.TITLE));
+        
+        // Can't reliably test dates yet - see TIKA-451 
+//        assertEquals("Sat Sep 15 10:02:31 BST 2007", metadata.get(Metadata.CREATION_DATE));
+//        assertEquals("Sat Sep 15 10:02:31 BST 2007", metadata.get(Metadata.LAST_MODIFIED));
+
+        String content = handler.toString();
+        assertTrue(content.contains("Apache Tika"));
+        assertTrue(content.contains("Tika - Content Analysis Toolkit"));
+        assertTrue(content.contains("incubator"));
+        assertTrue(content.contains("Apache Software Foundation"));
+    }
+}